metadata
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: txsa-sentiment-distilbert-HPO-full
results: []
txsa-sentiment-distilbert-HPO-full
This model is a fine-tuned version of distilbert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2792
- Accuracy: 0.963
- F1: 0.963
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 9.734765329618898e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 0.8024 | 1.0 | 3211 | 0.3262 | 0.893 | 0.893 |
| 0.3227 | 2.0 | 6422 | 0.2226 | 0.947 | 0.9470 |
| 0.1723 | 3.0 | 9633 | 0.2092 | 0.956 | 0.956 |
| 0.0996 | 4.0 | 12844 | 0.2710 | 0.96 | 0.96 |
| 0.0621 | 5.0 | 16055 | 0.2792 | 0.963 | 0.963 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2